mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 30 Mar 2022

239 papers

  1. End-to-End Table Question Answering via Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  2. Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect OraclesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  3. Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq GenerationEfficient LLM inference and serving → Speculative decoding
  4. Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  5. Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated LearningLLM safety and security → Federated unlearning and poisoning
  6. Self-Distillation from the Last Mini-Batch for Consistency RegularizationKnowledge distillation → General knowledge distillation methods
  7. Monitored Distillation for Positive Congruent Depth CompletionKnowledge distillation → Detection and dense prediction distillation
  8. Enhanced compound-protein binding affinity prediction by representing protein multimodal information via a coevolutionary strategy
  9. Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models
  10. INSPIRE: Distributed Bayesian Optimization for ImproviNg SPatIal REuse in Dense WLANs
  11. Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
  12. Decentralized Collaborative Learning Framework for Next POI Recommendation
  13. Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
  14. Position-based Prompting for Health Outcome Generation
  15. Evolutionary Programmer: Autonomously Creating Path Planning Programs based on Evolutionary Algorithms
  16. Scientometric Review of Artificial Intelligence for Operations & Maintenance of Wind Turbines: The Past, Present and Future
  17. Exosoul: ethical profiling in the digital world
  18. Artificial Intelligence: Framework of driving triggers to past, present and future applications and influencers of industry sector adoption
  19. Investigating Top-k White-Box and Transferable Black-box Attack
  20. Speech and the n-Back task as a lens into depression. How combining both may allow us to isolate different core symptoms of depression
  21. A quantum learning approach based on Hidden Markov Models for failure scenarios generation
  22. Reproducibility Issues for BERT-based Evaluation Metrics
  23. Ball 3D Localization From A Single Calibrated Image
  24. LEAD1.0: A Large-scale Annotated Dataset for Energy Anomaly Detection in Commercial Buildings
  25. Generation and Simulation of Synthetic Datasets with Copulas
  26. Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo
  27. VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers
  28. Automatic Detection of Expressed Emotion from Five-Minute Speech Samples: Challenges and Opportunities
  29. Analytic theory for the dynamics of wide quantum neural networks
  30. Task Adaptive Parameter Sharing for Multi-Task Learning
  31. Monte Carlo Tree Search based Hybrid Optimization of Variational Quantum Circuits
  32. Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion
  33. Towards Differential Relational Privacy and its use in Question Answering
  34. MAE-AST: Masked Autoencoding Audio Spectrogram Transformer
  35. Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation
  36. Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings
  37. Active Learning for Computationally Efficient Distribution of Binary Evolution Simulations
  38. To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo
  39. Face Relighting with Geometrically Consistent Shadows
  40. Learning the Effect of Registration Hyperparameters with HyperMorph
  41. Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels
  42. System Identification via Nuclear Norm Regularization
  43. PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition
  44. Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination
  45. Overcoming challenges in leveraging GANs for few-shot data augmentation
  46. Predicting Winners of the Reality TV Dating Show textitThe Bachelor Using Machine Learning Algorithms
  47. Generation of Speaker Representations Using Heterogeneous Training Batch Assembly
  48. Data-driven Prediction of Relevant Scenarios for Robust Combinatorial Optimization
  49. FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
  50. Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load
  51. Transformer Language Models without Positional Encodings Still Learn Positional Information
  52. Controllable Augmentations for Video Representation Learning
  53. Physics-constrained Unsupervised Learning of Partial Differential Equations using Meshes
  54. DDNeRF: Depth Distribution Neural Radiance Fields
  55. Federated Learning for the Classification of Tumor Infiltrating Lymphocytes
  56. TR-MOT: Multi-Object Tracking by Reference
  57. End-to-end Document Recognition and Understanding with Dessurt
  58. Knowledge-based Entity Prediction for Improved Machine Perception in Autonomous Systems
  59. A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization
  60. Enhancing Cancer Prediction in Challenging Screen-Detected Incident Lung Nodules Using Time-Series Deep Learning
  61. Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages?
  62. Learning Local Displacements for Point Cloud Completion
  63. Improving Speech Recognition for Indic Languages using Language Model
  64. Constrained Few-shot Class-incremental Learning
  65. Spatially Adaptive Online Prediction of Piecewise Regular Functions
  66. Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation
  67. Factored Adaptation for Non-Stationary Reinforcement Learning
  68. Code Switched and Code Mixed Speech Recognition for Indic languages
  69. Calibrating constitutive models with full-field data via physics informed neural networks
  70. Graph Refinement for Coreference Resolution
  71. Generating Scientific Articles with Machine Learning
  72. COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Training
  73. Towards Multimodal Depth Estimation from Light Fields
  74. Mind the gap: Challenges of deep learning approaches to Theory of Mind
  75. Identification of diffracted vortex beams at different propagation distances using deep learning
  76. Machine Learning Approaches for Non-Intrusive Home Absence Detection Based on Appliance Electrical Use
  77. Large-Scale Pre-training for Person Re-identification with Noisy Labels
  78. Understanding 3D Object Articulation in Internet Videos
  79. Learning Instance-Specific Adaptation for Cross-Domain Segmentation
  80. CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism
  81. L^3U-net: Low-Latency Lightweight U-net Based Image Segmentation Model for Parallel CNN Processors
  82. Exploring Plain Vision Transformer Backbones for Object Detection
  83. CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs
  84. Collaborative Transformers for Grounded Situation Recognition
  85. Unseen Classes at a Later Time? No Problem
  86. Fast Light-Weight Near-Field Photometric Stereo
  87. PromptDet: Towards Open-vocabulary Detection using Uncurated Images
  88. Vakyansh: ASR Toolkit for Low Resource Indic languages
  89. AdaMixer: A Fast-Converging Query-Based Object Detector
  90. An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection
  91. Fast, Accurate and Memory-Efficient Partial Permutation Synchronization
  92. Generative Spoken Dialogue Language Modeling
  93. Foveation-based Deep Video Compression without Motion Search
  94. RFNet-4D++: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds with Cross-Attention Spatio-Temporal Features
  95. On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
  96. Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries
  97. Zero Shot Crosslingual Eye-Tracking Data Prediction using Multilingual Transformer Models
  98. Remember to correct the bias when using deep learning for regression!
  99. Convergence of gradient descent for deep neural networks
  100. Weakly supervised causal representation learning
All 239
  1. TubeDETR: Spatio-Temporal Video Grounding with Transformers
  2. Balanced MSE for Imbalanced Visual Regression
  3. OPD: Single-view 3D Openable Part Detection
  4. Low-complexity Near-optimum Symbol Detection Based on Neural Enhancement of Factor Graphs
  5. The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation
  6. Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis
  7. Learning Fair Models without Sensitive Attributes: A Generative Approach
  8. PerfectDou: Dominating DouDizhu with Perfect Information Distillation
  9. Recognition of polar lows in Sentinel-1 SAR images with deep learning
  10. Online Motion Style Transfer for Interactive Character Control
  11. On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction
  12. CardioID: Mitigating the Effects of Irregular Cardiac Signals for Biometric Identification
  13. Slow-varying Dynamics Assisted Temporal Capsule Network for Machinery Remaining Useful Life Estimation
  14. Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis
  15. IGRF-RFE: A Hybrid Feature Selection Method for MLP-based Network Intrusion Detection on UNSW-NB15 Dataset
  16. Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
  17. Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain
  18. Generative Adversarial Networks for the fast simulation of the Time Projection Chamber responses at the MPD detector
  19. Learning multiobjective rough terrain traversability
  20. Optimization for Classical Machine Learning Problems on the GPU
  21. Multi-Robot Active Mapping via Neural Bipartite Graph Matching
  22. PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
  23. PEGG-Net: Pixel-Wise Efficient Grasp Generation in Complex Scenes
  24. Forecasting from LiDAR via Future Object Detection
  25. Acoustics-specific Piano Velocity Estimation
  26. AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift
  27. An Offset-Free Nonlinear MPC scheme for systems learned by Neural NARX models
  28. Reducing Learning Difficulties: One-Step Two-Critic Deep Reinforcement Learning for Inverter-based Volt-Var Control
  29. Region of Interest focused MRI to Synthetic CT Translation using Regression and Classification Multi-task Network
  30. FIRe: Fast Inverse Rendering using Directional and Signed Distance Functions
  31. The Weak Supervision Landscape
  32. CMMD: Cross-Metric Multi-Dimensional Root Cause Analysis
  33. Neural Pipeline for Zero-Shot Data-to-Text Generation
  34. Reinforcement Learning Guided by Provable Normative Compliance
  35. Interpretable Vertebral Fracture Diagnosis
  36. Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking
  37. DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decoder
  38. SeqTR: A Simple yet Universal Network for Visual Grounding
  39. Does Audio Deepfake Detection Generalize?
  40. How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning
  41. Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data
  42. Research topic trend prediction of scientific papers based on spatial enhancement and dynamic graph convolution network
  43. Physics Community Needs, Tools, and Resources for Machine Learning
  44. PP-YOLOE: An evolved version of YOLO
  45. InstaFormer: Instance-Aware Image-to-Image Translation with Transformer
  46. Co-Membership-based Generic Anomalous Communities Detection
  47. CycDA: Unsupervised Cycle Domain Adaptation from Image to Video
  48. Biclustering Algorithms Based on Metaheuristics: A Review
  49. Evaluation of semantic relations impact in query expansion-based retrieval systems
  50. Exploring ML testing in practice -- Lessons learned from an interactive rapid review with Axis Communications
  51. End to End Lip Synchronization with a Temporal AutoEncoder
  52. Hypergraphon Mean Field Games
  53. Phase-Aware Deep Speech Enhancement: It's All About The Frame Length
  54. Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection
  55. Acknowledging the Unknown for Multi-label Learning with Single Positive Labels
  56. APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction
  57. Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization
  58. Adaptive Divergence-based Non-negative Latent Factor Analysis
  59. Learning of Global Objective for Network Flow in Multi-Object Tracking
  60. Fair Contrastive Learning for Facial Attribute Classification
  61. Automatic Identification of Chemical Moieties
  62. Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimation
  63. On the Road to Online Adaptation for Semantic Image Segmentation
  64. FlowFormer: A Transformer Architecture for Optical Flow
  65. Auto-MLM: Improved Contrastive Learning for Self-supervised Multi-lingual Knowledge Retrieval
  66. Dynamic Model Tree for Interpretable Data Stream Learning
  67. Marginalized Operators for Off-policy Reinforcement Learning
  68. Anticipatory Counterplanning
  69. Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling
  70. FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing
  71. Symbolic music generation conditioned on continuous-valued emotions
  72. Rabbit, toad, and the Moon: Can machine categorize them into one class?
  73. AdaGrid: Adaptive Grid Search for Link Prediction Training Objective
  74. Recommendation of Compatible Outfits Conditioned on Style
  75. BBE-LSWCM: A Bootstrapped Ensemble of Long and Short Window Clickstream Models
  76. Tampered VAE for Improved Satellite Image Time Series Classification
  77. Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis
  78. Sensor Data Validation and Driving Safety in Autonomous Driving Systems
  79. An Overview of Indian Language Datasets used for Text Summarization
  80. SIT: A Bionic and Non-Linear Neuron for Spiking Neural Network
  81. A Fast Transformer-based General-Purpose Lossless Compressor
  82. Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version
  83. Preliminary experiments on thermal emissivity adjustment for face images
  84. Contribution of the Temperature of the Objects to the Problem of Thermal Imaging Focusing
  85. Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation
  86. Continual Normalization: Rethinking Batch Normalization for Online Continual Learning
  87. Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE
  88. Neighbor Enhanced Graph Convolutional Networks for Node Classification and Recommendation
  89. Global Tracking via Ensemble of Local Trackers
  90. Omni-DETR: Omni-Supervised Object Detection with Transformers
  91. Polarized deep diffractive neural network for classification, generation, multiplexing and de-multiplexing of orbital angular momentum modes
  92. STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction
  93. An Efficient Anchor-free Universal Lesion Detection in CT-scans
  94. Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models
  95. Learning Program Representations for Food Images and Cooking Recipes
  96. An Improved Greedy Algorithm for Subset Selection in Linear Estimation
  97. Decision-Focused Learning without Differentiable Optimization: Learning Locally Optimized Decision Losses
  98. Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention
  99. AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval
  100. Understanding Graph Convolutional Networks for Text Classification
  101. Self-supervised 360circ Room Layout Estimation
  102. Automatic Facial Skin Feature Detection for Everyone
  103. Coarse-to-Fine Recursive Speech Separation for Unknown Number of Speakers
  104. Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
  105. Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds
  106. An Iterative Co-Training Transductive Framework for Zero Shot Learning
  107. Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks
  108. Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels
  109. Enhancing Zero-Shot Many to Many Voice Conversion with Self-Attention VAE
  110. How Deep is Your Art: An Experimental Study on the Limits of Artistic Understanding in a Single-Task, Single-Modality Neural Network
  111. ReplaceBlock: An improved regularization method based on background information
  112. Span Classification with Structured Information for Disfluency Detection in Spoken Utterances
  113. Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension
  114. Longitudinal Fairness with Censorship
  115. ITTR: Unpaired Image-to-Image Translation with Transformers
  116. Towards Collaborative Intelligence: Routability Estimation based on Decentralized Private Data
  117. Prognosis of Rotor Parts Fly-off Based on Cascade Classification and Online Prediction Ability Index
  118. Theory of Acceleration of Decision Making by Correlated Time Sequences
  119. Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds
  120. StyleFool: Fooling Video Classification Systems via Style Transfer
  121. TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models
  122. Optimal Learning
  123. The Sound of Bounding-Boxes
  124. Does Configuration Encoding Matter in Learning Software Performance? An Empirical Study on Encoding Schemes
  125. Fine-Grained Object Classification via Self-Supervised Pose Alignment
  126. VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics
  127. Iterative Deep Homography Estimation
  128. DELTA: Dynamically Optimizing GPU Memory beyond Tensor Recomputation
  129. Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models
  130. Multi-scale Speaker Diarization with Dynamic Scale Weighting
  131. Higher-Order Generalization Bounds: Learning Deep Probabilistic Programs via PAC-Bayes Objectives
  132. A meta-probabilistic-programming language for bisimulation of probabilistic and non-well-founded type systems
  133. Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation
  134. Federated Domain Adaptation for ASR with Full Self-Supervision
  135. PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation
  136. Using Active Speaker Faces for Diarization in TV shows
  137. Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature
  138. High-resolution Face Swapping via Latent Semantics Disentanglement
  139. Investigating the Properties of Neural Network Representations in Reinforcement Learning